© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 116073
    Prev
    Next
    INDEX
    Explanations

    different

    np_acts-logits-general · gemini-2.5-flash-lite

    PlayStation mascot, based on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    បើ
    0.46
    _
    0.46
     повышения
    0.45
     क्विक
    0.43
    ization
    0.43
    jährige
    0.42
     पैकेज
    0.42
     призна
    0.41
     किराए
    0.41
    rence
    0.40
    POSITIVE LOGITS
     amea
    0.51
     molécules
    0.50
    ზ
    0.50
    université
    0.49
    सेप्शन
    0.48
     algebraica
    0.48
    ܘܢ
    0.47
    两侧
    0.47
    ☚
    0.47
     ܠ
    0.46
    Activations Density 0.001%

    No Known Activations